Text-to-Speech
Turn any text into lifelike, natural-sounding audio. Multiple voices and languages for accessibility, e-learning, and content creation.
Create custom voices from a text description, with natural-language control over timbre, emotion, and accent.
What you can do with Qwen3 TTS VoiceDesign.
Turn any text into lifelike, natural-sounding audio. Multiple voices and languages for accessibility, e-learning, and content creation.
Text Length
10–5000 characters
Output Format
MP3 at 24 kHz
Default Voice
default
Integrate Qwen3 TTS VoiceDesign into your app with a single API call.
POST https://api.deapi.ai/api/v1/client/txt2audio
curl · deAPI txt2audio
curl -X 'POST' \ 'https://api.deapi.ai/api/v1/client/txt2audio' \ -H 'accept: application/json' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "model": "Qwen3_TTS_12Hz_1_7B_VoiceDesign", "text": "Hello, welcome to deAPI. The fastest way to use AI models.", "voice": "af_heart" }'{ "model": "Qwen3_TTS_12Hz_1_7B_VoiceDesign", "text": "Hello, welcome to deAPI. The fastest way to use AI models.", "voice": "af_heart" }
Tip: The API returns a request_id. Use webhooks (recommended) or poll GET /request-status/{request_id} for results.
Need an API key?
Sign up for free and get $5 in credits to start.
Other models with similar capabilities you might find useful.
41 voices (male & female). 7 languages: EN-US, EN-GB, ES, FR-FR, HI, IT, PT-BR. Output: MP3/FLAC at 24kHz.
23 languages: EN, ES, FR, DE, ZH, JA, KO, AR, HI, PL and more. Emotion exaggeration control. Built-in AI watermarking. Output: WAV/FLAC.
9 premium voices (male & female). 10 languages: EN, ZH, JA, KO, DE, FR, RU, PT, ES, IT. Instruction-driven emotion & prosody control. Streaming with 97ms latency. Output: MP3 at 24...
Get $5 in free credits and start generating with Qwen3 TTS VoiceDesign.